© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9439
    Prev
    Next
    INDEX
    Explanations

    friendly staff, service, or environment

    np_acts-logits-general · gemini-2.5-flash-lite

    friendly, kind, gentle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鏂
    0.46
    idir
    0.45
     OW
    0.43
     dwRes
    0.43
     Dir
    0.41
     Really
    0.41
     angu
    0.41
     Infer
    0.40
    </code>
    0.40
    ograms
    0.40
    POSITIVE LOGITS
    friendly
    0.87
     friendly
    0.84
    warm
    0.75
    Friendly
    0.72
    友好
    0.70
    Warm
    0.67
     Friendly
    0.66
     hangat
    0.66
     warm
    0.64
     amable
    0.61
    Activations Density 0.166%

    No Known Activations